// teleport guide · Browser · official

Teleport Playwright MCP — read-only, P2P, zero cloud

Microsoft's Playwright MCP drives a browser via accessibility snapshots instead of screenshots. Sharing it over MCPWire gives a remote agent a real browser on your machine — pair --confirm with browser_click and browser_type so nothing happens without your y/n. This guide maps all 10 tools of @playwright/mcp by blast radius, then gives you the exact command to share it with a remote teammate's AI agent — capability without credentials.

4SAFE to expose

5CAUTION

1KEEP LOCAL

0servers involved

host terminal — read-only share command

npx -y mcpwire share --allow "browser_snapshot,browser_screenshot,browser_console_messages,browser_close" --redact-secrets --ttl 30m -- npx -y @playwright/mcp

Only the 4 read-only tools are exposed; the other 6 are invisible to the peer (filtered from tools/list and blocked if forced). Tunnel dies in 30 minutes. Add --confirm to approve every call, or --max-calls 20 for a hard budget.

peer config — claude_desktop_config.json / .cursor/mcp.json

{
  "mcpServers": {
    "teleported-playwright": {
      "command": "npx",
      "args": [
        "-y",
        "mcpwire",
        "join",
        "wire://<TICKET_FROM_HOST_BANNER>"
      ]
    }
  }
}

🛡️ tool risk map — Playwright

tool	risk	notes
`browser_navigate`	CAUTION	Opens URLs on your machine.
`browser_snapshot`	SAFE	Accessibility tree capture.
`browser_screenshot`	SAFE	Screenshot capture.
`browser_click`	CAUTION	Clicks page elements.
`browser_type`	CAUTION	Types into fields — could type credentials.
`browser_fill_form`	CAUTION	Batch form filling.
`browser_press_key`	CAUTION	Key events.
`browser_evaluate`	HIGH RISK	Runs arbitrary JS in the page.
`browser_console_messages`	SAFE	Reads console output.
`browser_close`	SAFE	Closes the page.

🔒 Why not just share your token?

Playwright's credential would grant the full toolset to a foreign LLM — including browser_evaluate. With mcpwire the credential stays in your env; the peer only ever holds an expiring wire:// capability scoped to 4 tools.

🎥 Audit everything

Add --record session.wirelog and every call, block and redaction is logged locally. Drag the file into mcpwire.co/replay for a DevTools-style waterfall of what the remote agent actually did.

🔁 Works with every MCP client

Claude Desktop, Cursor, Windsurf, Cline — anything speaking MCP over stdio. Your peer pastes the snippet above; you keep the kill-switch (Ctrl+C) in your terminal.

What happens if the peer's agent tries to call a blocked Playwright tool?

The request never reaches your MCP server. mcpwire answers with a JSON-RPC error (-32601 [MCPWire Firewall]) and logs the attempt — the tool doesn't exist from the agent's point of view, so well-behaved agents won't even try.

Can I expose the caution-level tools too?

Yes — just add them to --allow or run with --confirm so each call waits for your y/n in the host terminal. The risk map above tells you exactly what you'd be signing up for.

Is the traffic really serverless?

Yes. Discovery goes through the public Hyperswarm DHT; the data path is a direct Noise-encrypted socket between the two machines (UDP hole punching). If both NATs are stubborn, Hyperswarm routes through community relays — which only see ciphertext.

← all teleport guides ⚡ open the policy builder

🔒 MCPWire Enterprise & Team Mesh (Early Access)

Need persistent wire://your-company/db namespaces, SSO / GitHub identity verification before the P2P handshake, and centralized audit logs for compliance (SOC2 / ISO)?